As a general rule, the cover image that is randomly placed is the original image running 512X768 locally, without facial restoration, high-definition resolution restoration, or lora addition.
Local parameters: DPM++2M Karras
Number of iteration steps: 25 cfg: 6
Positive prompt words for the photo: Canon RF85mm f/1.2,masterpiece,best quality,ultra highres,1 girl,(korean mixed,kpop idol:1.2),solo,white_shiny_skin,black eyes,necklace,brown_long_wavy_hair,red_shiny_lips,eyelashes,bangs, make-up,shiny,Pore,skin texture,bracelet,offshoulder,see-through,big breasts
I think it's pretty good at least for drawing pictures. I copy the prompt words and draw them as I like, and I almost don't have to pick them. As for the full body high score repair pictures, I haven’t had time to test them yet.
Listening to the heart-rending roar of the small graphics card with 4G video memory, it's a pity that I can't build the model myself. Fortunately, I am not a professional, I just do it for fun after work. . .
No showcase images available, the model won't be visible to others.
Run3.7K
Version Detail
SD 1.5
Project Permissions
Use in TENSOR GREEN Online
As a online training base model on TENSOR GREEN
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges
Commercial Use
Comments
Related Posts
Describe the image you want to generate, then press Enter to send.